X-Git-Url: http://git.onelab.eu/?a=blobdiff_plain;f=arch%2Fi386%2Fkernel%2Fcpu%2Fintel_cacheinfo.c;fp=arch%2Fi386%2Fkernel%2Fcpu%2Fintel_cacheinfo.c;h=5c43be47587f5d4b9875e4c45070027cdb829d95;hb=16c70f8c1b54b61c3b951b6fb220df250fe09b32;hp=f3f2bc8835a5d5888da1dba3866820bffa432a81;hpb=4e76c8a9fa413ccc09d3f7f664183dcce3555d57;p=linux-2.6.git diff --git a/arch/i386/kernel/cpu/intel_cacheinfo.c b/arch/i386/kernel/cpu/intel_cacheinfo.c index f3f2bc883..5c43be475 100644 --- a/arch/i386/kernel/cpu/intel_cacheinfo.c +++ b/arch/i386/kernel/cpu/intel_cacheinfo.c @@ -4,6 +4,7 @@ * Changes: * Venkatesh Pallipadi : Adding cache identification through cpuid(4) * Ashok Raj : Work with CPU hotplug infrastructure. + * Andi Kleen : CPUID4 emulation on AMD. */ #include @@ -130,25 +131,111 @@ struct _cpuid4_info { cpumask_t shared_cpu_map; }; -static unsigned short num_cache_leaves; +unsigned short num_cache_leaves; + +/* AMD doesn't have CPUID4. Emulate it here to report the same + information to the user. This makes some assumptions about the machine: + No L3, L2 not shared, no SMT etc. that is currently true on AMD CPUs. + + In theory the TLBs could be reported as fake type (they are in "dummy"). + Maybe later */ +union l1_cache { + struct { + unsigned line_size : 8; + unsigned lines_per_tag : 8; + unsigned assoc : 8; + unsigned size_in_kb : 8; + }; + unsigned val; +}; + +union l2_cache { + struct { + unsigned line_size : 8; + unsigned lines_per_tag : 4; + unsigned assoc : 4; + unsigned size_in_kb : 16; + }; + unsigned val; +}; + +static const unsigned short assocs[] = { + [1] = 1, [2] = 2, [4] = 4, [6] = 8, + [8] = 16, + [0xf] = 0xffff // ?? + }; +static const unsigned char levels[] = { 1, 1, 2 }; +static const unsigned char types[] = { 1, 2, 3 }; + +static void __cpuinit amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax, + union _cpuid4_leaf_ebx *ebx, + union _cpuid4_leaf_ecx *ecx) +{ + unsigned dummy; + unsigned line_size, lines_per_tag, assoc, size_in_kb; + union l1_cache l1i, l1d; + union l2_cache l2; + + eax->full = 0; + ebx->full = 0; + ecx->full = 0; + + cpuid(0x80000005, &dummy, &dummy, &l1d.val, &l1i.val); + cpuid(0x80000006, &dummy, &dummy, &l2.val, &dummy); + + if (leaf > 2 || !l1d.val || !l1i.val || !l2.val) + return; + + eax->split.is_self_initializing = 1; + eax->split.type = types[leaf]; + eax->split.level = levels[leaf]; + eax->split.num_threads_sharing = 0; + eax->split.num_cores_on_die = current_cpu_data.x86_max_cores - 1; + + if (leaf <= 1) { + union l1_cache *l1 = leaf == 0 ? &l1d : &l1i; + assoc = l1->assoc; + line_size = l1->line_size; + lines_per_tag = l1->lines_per_tag; + size_in_kb = l1->size_in_kb; + } else { + assoc = l2.assoc; + line_size = l2.line_size; + lines_per_tag = l2.lines_per_tag; + /* cpu_data has errata corrections for K7 applied */ + size_in_kb = current_cpu_data.x86_cache_size; + } + + if (assoc == 0xf) + eax->split.is_fully_associative = 1; + ebx->split.coherency_line_size = line_size - 1; + ebx->split.ways_of_associativity = assocs[assoc] - 1; + ebx->split.physical_line_partition = lines_per_tag - 1; + ecx->split.number_of_sets = (size_in_kb * 1024) / line_size / + (ebx->split.ways_of_associativity + 1) - 1; +} static int __cpuinit cpuid4_cache_lookup(int index, struct _cpuid4_info *this_leaf) { - unsigned int eax, ebx, ecx, edx; - union _cpuid4_leaf_eax cache_eax; + union _cpuid4_leaf_eax eax; + union _cpuid4_leaf_ebx ebx; + union _cpuid4_leaf_ecx ecx; + unsigned edx; - cpuid_count(4, index, &eax, &ebx, &ecx, &edx); - cache_eax.full = eax; - if (cache_eax.split.type == CACHE_TYPE_NULL) + if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) + amd_cpuid4(index, &eax, &ebx, &ecx); + else + cpuid_count(4, index, &eax.full, &ebx.full, &ecx.full, &edx); + if (eax.split.type == CACHE_TYPE_NULL) return -EIO; /* better error ? */ - this_leaf->eax.full = eax; - this_leaf->ebx.full = ebx; - this_leaf->ecx.full = ecx; - this_leaf->size = (this_leaf->ecx.split.number_of_sets + 1) * - (this_leaf->ebx.split.coherency_line_size + 1) * - (this_leaf->ebx.split.physical_line_partition + 1) * - (this_leaf->ebx.split.ways_of_associativity + 1); + this_leaf->eax = eax; + this_leaf->ebx = ebx; + this_leaf->ecx = ecx; + this_leaf->size = (ecx.split.number_of_sets + 1) * + (ebx.split.coherency_line_size + 1) * + (ebx.split.physical_line_partition + 1) * + (ebx.split.ways_of_associativity + 1); return 0; } @@ -174,7 +261,7 @@ unsigned int __cpuinit init_intel_cacheinfo(struct cpuinfo_x86 *c) unsigned int new_l1d = 0, new_l1i = 0; /* Cache sizes from cpuid(4) */ unsigned int new_l2 = 0, new_l3 = 0, i; /* Cache sizes from cpuid(4) */ unsigned int l2_id = 0, l3_id = 0, num_threads_sharing, index_msb; -#ifdef CONFIG_SMP +#ifdef CONFIG_X86_HT unsigned int cpu = (c == &boot_cpu_data) ? 0 : (c - cpu_data); #endif @@ -296,14 +383,14 @@ unsigned int __cpuinit init_intel_cacheinfo(struct cpuinfo_x86 *c) if (new_l2) { l2 = new_l2; -#ifdef CONFIG_SMP +#ifdef CONFIG_X86_HT cpu_llc_id[cpu] = l2_id; #endif } if (new_l3) { l3 = new_l3; -#ifdef CONFIG_SMP +#ifdef CONFIG_X86_HT cpu_llc_id[cpu] = l3_id; #endif } @@ -628,7 +715,7 @@ static int __cpuinit cache_add_dev(struct sys_device * sys_dev) return retval; } -static void cache_remove_dev(struct sys_device * sys_dev) +static void __cpuexit cache_remove_dev(struct sys_device * sys_dev) { unsigned int cpu = sys_dev->id; unsigned long i; @@ -642,7 +729,7 @@ static void cache_remove_dev(struct sys_device * sys_dev) return; } -static int cacheinfo_cpu_callback(struct notifier_block *nfb, +static int __cpuinit cacheinfo_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) { unsigned int cpu = (unsigned long)hcpu; @@ -660,7 +747,7 @@ static int cacheinfo_cpu_callback(struct notifier_block *nfb, return NOTIFY_OK; } -static struct notifier_block cacheinfo_cpu_notifier = +static struct notifier_block __cpuinitdata cacheinfo_cpu_notifier = { .notifier_call = cacheinfo_cpu_callback, }; @@ -672,7 +759,7 @@ static int __cpuinit cache_sysfs_init(void) if (num_cache_leaves == 0) return 0; - register_cpu_notifier(&cacheinfo_cpu_notifier); + register_hotcpu_notifier(&cacheinfo_cpu_notifier); for_each_online_cpu(i) { cacheinfo_cpu_callback(&cacheinfo_cpu_notifier, CPU_ONLINE,